---
title: "Sentiment Analysis for for Tweets in Ukraine March 2022 by @DayvonnJ & Nilay Vinchhi"
output: 
  flexdashboard::flex_dashboard:
    orientation: columns
    vertical_layout: fill
    social: menu
    source_code: embed
    theme: readable

---

```{r setup, include=T}
library(flexdashboard)
library(tidyverse,quietly=T)
library(data.table,quietly=T)
library(htmltools)
library(htmlTable,quietly=T)
library(viridis,quietly=T)
library(plotly,quietly=T)
library(scales,quietly=T)
library(crosstalk)
library(maps)
library(flexdashboard)
library(shiny)
library(knitr)
library(kableExtra)
library(tidyverse)
library(plotly)
library(crosstalk)
library(bslib)
library(shiny)
library(tidyverse)
library(quanteda)
library(quanteda.textplots)
library(sentimentr)
library(viridis)
library(dplyr)
library(tidytext)
library(textdata)
library(stringr)
library(janeaustenr)
library(esquisse)
library(ggplot2)
library(plotly)
library(quantmod)
library(lubridate)
library(wordcloud)
library(sentiment.ai)
```



About {data-navmenu="Explore"}
===================================== 

Column {data-width=200}
-------------------------------------

### About this flexdashboard

Textual data analysis is an emerging field of NLP; This dashboard is an approach to understanding the sentiments and emotions of people in the war-zoned country using Twitter textual data. This dashboard is also an attempt to visualize the data efficiently and beautifully.

Column {data-width=800}
-------------------------------------

### Areas covered

```{r jan222017-map1,echo=F}
emotion <-read.csv("emotion.csv")
sentiment <-read.csv("sentiment.csv")
uk <- readxl::read_xlsx("ukraine.xlsx")
uk <- rename(uk, Date = ï..Data.created_at)
shared_data <- uk %>%
  select(Date, sentiment.x, class.x, Data.retweet_count, Data.full_text, Data.user.screen_name, Data.url, phrase.x, Data.user.location) %>%
  mutate(sentiment.x = round(sentiment.x, 4)) %>%
  SharedData$new()

p <- shared_data %>% 
  plot_ly(type='scatter', mode = 'markers', x = ~Date, y = ~sentiment.x, color= ~class.x, colors=c("#FFD500","#005BBB"),size = ~Data.retweet_count, hovertemplate = paste("Tweet:  
",uk$Data.full_text, "
 Tweet by:  @",uk$Data.user.screen_name,"
 Tweet Link:  ",uk$Data.url,"
 Retweets:  ",uk$Data.retweet_count,"
 Tweet Sentiment Score: ", uk$sentiment.x,"
 Sentiment Phrase: ", uk$phrase.x, "
 User Provided Location: ", uk$Data.user.location,"
 Tweeted on:  
", uk$Date), autosize = TRUE, title = "Sentiment Analysis for Tweets in March 2022, Ukraine",
                        xaxis = list(rangeslider = list(type = "date"), title = "Date"),
                        yaxis = list(title = "Sentiment Score"),
                        legend = list(title=list(text="Sentiment Class")))

                        

# Combining several selectors
bscols(widths = c(4, 6),
       list(
            filter_checkbox(id = "class", label = "Sentiment Class",
                    sharedData = shared_data, group = ~class.x),
            filter_select(id = "phrase", label = "Sentiment Phrase",
                    sharedData = shared_data, group = ~phrase.x),
            filter_slider(id = "slider_sc", label = "Sentiment Score",
                    sharedData = shared_data, column = ~sentiment.x)
      ),
       p)
```


Spatial Components {.storyboard data-navmenu="Explore"}
=========================================

### Most Mentioned Cities

```{r}
shiny::includeHTML("CM.html")
```

### User Provided GeoLocation

```{r}
shiny::includeHTML("UL.html")
```


Sentiment Analysis {.storyboard data-navmenu="Explore"}
===================================== 

### Emotions Count with nrc sentiment (syuzhet)

```{r, eval=T}

col <- colorRampPalette(c("#ffd500", "#bfb72f", "#bfb72f", "#2b6f9c", "#005bbb"))
col2 <- colorRampPalette(c("#005bbb","#2b6f9c", "#bfb72f","#bfb72f", "#ffd500" ))

f1 <-  ggplot(emotion) +
   aes(x = reorder(phrase,-count), fill = class, weight = count) +
   geom_bar() +
   scale_fill_manual(values = c(negative = "#FFD500", 
  positive = "#005BBB")) +
   labs(x = "Emotion", y = "Frequency", title = "Tweet Emotions", subtitle = "Emotions counted by Positive-Negative Classes of tweets about Russia-Ukraine War; March 2022", caption = "Data visualization by Dayonn J., @DayvonnJ, Nilay V., @nilayvinchhi., Data source: Twitter API, produced using c(ggplot2, sentiment.ai, nrc sentiment) Libraries in R 4.1.3", 
   fill = "Sentiment Class") +
  geom_text(aes(x=reorder(phrase,-count), y = count, label = count), nudge_y=50)
ggplotly(p = f1)
```

### Sentiment Analysis with Bing Lexicon

```{r}
text.sentiment <- tibble(text = str_to_lower(sentiment$phrase))

bing_word_counts <- text.sentiment %>% unnest_tokens(output = word, input = text) %>%
  inner_join(get_sentiments("bing")) %>%
  count(word, sentiment, sort = TRUE)

bing_top_10_words_by_sentiment <- bing_word_counts %>% 
  group_by(sentiment) %>% 
  slice_max(order_by = n, n = 10) %>% 
  ungroup() %>% 
  mutate(word = reorder(word, n)) 

f2 <-  bing_top_10_words_by_sentiment %>% 
    ggplot(aes(word, n, fill = sentiment)) + 
    geom_col(show.legend = FALSE) + 
    facet_wrap(~sentiment, scales = "free_y") + 
    scale_fill_manual(values = c(negative = "#FFD500", 
  positive = "#005BBB"))+
      coord_flip()+
       labs(x = NULL, y = "Phrases contributing to Sentiment Class", title = "Phrases by Sentiment Class for Tweets", subtitle = "Phrases counted by Positive-Negative Classes of tweets about Russia-Ukraine War; March 2022", caption = "Data visualization by Dayonn J., @DayvonnJ, Nilay V., @nilayvinchhi., Data source: Twitter API, produced using c(ggplot2, nrc sentiment) Libraries in R 4.1.3")+
    geom_text(aes(x=word, y = n, label = n), nudge_y=10, color= "grey")+
  theme_minimal()

ggplotly(p = f2)

```

### Sentiment Analysis  using Loughran Lexicon

```{r}
loughran_word_counts <- text.sentiment %>% unnest_tokens(output = word, input = text) %>%
  inner_join(get_sentiments("loughran")) %>%
  count(word, sentiment, sort = TRUE)

loughran_top_10_words_by_sentiment <- loughran_word_counts %>% 
  group_by(sentiment) %>% 
  slice_max(order_by = n, n = 10) %>% 
  ungroup() %>%
  mutate(word = reorder(word, n))

f3 <-  loughran_top_10_words_by_sentiment %>% 
    ggplot(aes(word, n, fill = sentiment)) + 
    geom_col(show.legend = FALSE) + 
    facet_wrap(~sentiment, scales = "free_y") + 
     coord_flip()+
      scale_fill_manual(values = c(negative = "#FFD500", positive = "#005BBB", uncertainty = "#eacb10", constraining = "#95a24e", litigious = "#55847d"))+
         labs(x = NULL, y = "Phrases contributing to Sentiments", title = "Phrases contributing to Sentiments for Tweets", subtitle = "Phrases counted by Sentiments of tweets about Russia-Ukraine War; March 2022", caption = "Data visualization by Dayonn J., @DayvonnJ, Nilay V., @nilayvinchhi., Data source: Twitter API, produced using c(ggplot2, tidytext, tidyverse, syuzhet) Libraries in R 4.1.3")+
      geom_text(aes(x=word, y = n, label = n), nudge_y=10, color= "grey")+
    theme_minimal()
ggplotly(p=f3)
```


```{r}